Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    roof materials and repair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    म
    0.91
    r
    0.85
    t
    0.83
    a
    0.82
    )}
    0.80
    ंश
    0.77
    d
    0.77
    the
    0.77
    ł
    0.76
    지
    0.76
    POSITIVE LOGITS
     Roofing
    0.82
     aren
    0.81
     Wasn
    0.81
    $
    0.79
    O
    0.77
     you
    0.73
    roof
    0.73
    ל
    0.73
    एम
    0.70
     Roof
    0.70
    Act Density 0.002%

    No Known Activations